from sklearn_benchmarks.reporting.hp_match import HpMatchReporting
import pandas as pd
pd.set_option('display.max_colwidth', None)
pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)

scikit-learn vs. scikit-learn-intelex (Intel® oneAPI)

measurements = ['iteration_throughput', 'latency', 'mean_duration_sklearn', 'mean_duration_sklearnex', 'speedup', 'std_duration_sklearn', 'std_duration_sklearnex', 'std_speedup']

def get_position(string):
    if "mean_duration" in string:
        return 3
    elif "std_duration" in string:
        return 2
    elif "score" in string:
        return 1
    elif "speedup" in string:
        return 0
    else:
        return -1

sorted(measurements, key=get_position, reverse=True) 

['mean_duration_sklearn',
 'mean_duration_sklearnex',
 'std_duration_sklearn',
 'std_duration_sklearnex',
 'speedup',
 'std_speedup',
 'iteration_throughput',
 'latency']

reporting = HpMatchReporting(against_lib="sklearnex", config="config.yml", log_scale=True)
reporting.make_report()

We assume here there is a perfect match between the hyperparameters of both librairies. For a given set of parameters and a given dataset, we compute the speedup time scikit-learn / time sklearnex. For instance, a speedup of 2 means that sklearnex is twice as fast as scikit-learn for a given set of parameters and a given dataset.

KNeighborsClassifier_brute_force

scikit-learn-intelex (2021.20210705.191215) vs. scikit-learn (1.0.dev0)

Speedup barplots

All estimators share the following parameters: algorithm=brute.

WARNING! Mismatch between validation scores for 14 prediction (58.33%). The observed differences can be found in the diff_accuracy_scores column. The chosen difference threshold is 0.001 for accuracy_score. See details in the dataframe below.

	estimator	function	n_samples_train	n_samples	n_features	parameters_digest	dataset_digest	mean_duration_sklearn	std_duration_sklearn	n_iter	iteration_throughput	latency	algorithm	n_jobs	n_neighbors	accuracy_score_sklearn	mean_duration_sklearnex	std_duration_sklearnex	accuracy_score_sklearnex	speedup	std_speedup	diff_accuracy_scores
1	KNeighborsClassifier_brute_force	predict	100000	1000	100	e70d8e7886766d41f30889506baa1e67	2cf49829391aa7891e877f2ed070adf0	2.345982	0.197174	NaN	0.000341	0.002346	brute	-1	1	0.663	0.471125	0.006206	0.687	4.979534	4.979966	0.024
4	KNeighborsClassifier_brute_force	predict	100000	1000	100	22d5eac4a4146149b35eae6914921514	2cf49829391aa7891e877f2ed070adf0	3.136109	0.100838	NaN	0.000255	0.003136	brute	-1	5	0.757	0.472683	0.006361	0.742	6.634696	6.635296	0.015
7	KNeighborsClassifier_brute_force	predict	100000	1000	100	16f94fc93942ff7ece860c9b0f64645f	2cf49829391aa7891e877f2ed070adf0	2.443875	0.027407	NaN	0.000327	0.002444	brute	1	100	0.882	0.536968	0.007184	0.875	4.551247	4.551654	0.007
8	KNeighborsClassifier_brute_force	predict	100000	1	100	16f94fc93942ff7ece860c9b0f64645f	2cf49829391aa7891e877f2ed070adf0	0.025788	0.002638	NaN	0.000031	0.025788	brute	1	100	1.000	0.011406	0.000669	0.000	2.260944	2.264826	1.000
10	KNeighborsClassifier_brute_force	predict	100000	1000	100	2d5f2b2c02d77766434d9e5033b4a76c	2cf49829391aa7891e877f2ed070adf0	3.139071	0.062996	NaN	0.000255	0.003139	brute	-1	100	0.882	0.529779	0.010274	0.875	5.925245	5.926359	0.007
11	KNeighborsClassifier_brute_force	predict	100000	1	100	2d5f2b2c02d77766434d9e5033b4a76c	2cf49829391aa7891e877f2ed070adf0	0.028726	0.002505	NaN	0.000028	0.028726	brute	-1	100	1.000	0.011955	0.001017	0.000	2.402805	2.411487	1.000
13	KNeighborsClassifier_brute_force	predict	100000	1000	100	efac583623711d395ddae7a1e881ff68	2cf49829391aa7891e877f2ed070adf0	2.442894	0.022442	NaN	0.000327	0.002443	brute	1	5	0.757	0.466291	0.009039	0.742	5.238993	5.239977	0.015
16	KNeighborsClassifier_brute_force	predict	100000	1000	100	b79d63bb7670c492de5c3befac58fe29	2cf49829391aa7891e877f2ed070adf0	1.621578	0.010942	NaN	0.000493	0.001622	brute	1	1	0.663	0.470931	0.013045	0.687	3.443344	3.444664	0.024
19	KNeighborsClassifier_brute_force	predict	100000	1000	2	e70d8e7886766d41f30889506baa1e67	88843f54689e3271092f70126e1de585	1.851052	0.028637	NaN	0.000009	0.001851	brute	-1	1	0.896	0.105019	0.007501	0.967	17.625800	17.670700	0.071
22	KNeighborsClassifier_brute_force	predict	100000	1000	2	22d5eac4a4146149b35eae6914921514	88843f54689e3271092f70126e1de585	2.809051	0.070351	NaN	0.000006	0.002809	brute	-1	5	0.922	0.102533	0.002546	0.974	27.396503	27.404945	0.052
25	KNeighborsClassifier_brute_force	predict	100000	1000	2	16f94fc93942ff7ece860c9b0f64645f	88843f54689e3271092f70126e1de585	2.212984	0.031356	NaN	0.000007	0.002213	brute	1	100	0.929	0.157741	0.002225	0.975	14.029200	14.030595	0.046
28	KNeighborsClassifier_brute_force	predict	100000	1000	2	2d5f2b2c02d77766434d9e5033b4a76c	88843f54689e3271092f70126e1de585	2.779325	0.060005	NaN	0.000006	0.002779	brute	-1	100	0.929	0.158738	0.003885	0.975	17.508870	17.514113	0.046
31	KNeighborsClassifier_brute_force	predict	100000	1000	2	efac583623711d395ddae7a1e881ff68	88843f54689e3271092f70126e1de585	2.256987	0.044696	NaN	0.000007	0.002257	brute	1	5	0.922	0.102296	0.001294	0.974	22.063359	22.065123	0.052
34	KNeighborsClassifier_brute_force	predict	100000	1000	2	b79d63bb7670c492de5c3befac58fe29	88843f54689e3271092f70126e1de585	1.317206	0.014492	NaN	0.000012	0.001317	brute	1	1	0.896	0.101021	0.002322	0.967	13.038872	13.042315	0.071

Raw results

	estimator	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_jobs	n_neighbors	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	KNeighborsClassifier_brute_force	fit	100000	100000	100	0.014	0.001	5.744	0.0	-1	1	0.059	0.005	0.236	0.237	See	See
3	KNeighborsClassifier_brute_force	fit	100000	100000	100	0.013	0.001	5.935	0.0	-1	5	0.062	0.005	0.219	0.220	See	See
6	KNeighborsClassifier_brute_force	fit	100000	100000	100	0.014	0.000	5.890	0.0	1	100	0.059	0.001	0.229	0.229	See	See
9	KNeighborsClassifier_brute_force	fit	100000	100000	100	0.014	0.001	5.652	0.0	-1	100	0.056	0.002	0.252	0.252	See	See
12	KNeighborsClassifier_brute_force	fit	100000	100000	100	0.014	0.001	5.914	0.0	1	5	0.059	0.001	0.229	0.229	See	See
15	KNeighborsClassifier_brute_force	fit	100000	100000	100	0.015	0.001	5.358	0.0	1	1	0.057	0.002	0.261	0.261	See	See
18	KNeighborsClassifier_brute_force	fit	100000	100000	2	0.005	0.000	0.314	0.0	-1	1	0.009	0.001	0.585	0.588	See	See
21	KNeighborsClassifier_brute_force	fit	100000	100000	2	0.005	0.000	0.326	0.0	-1	5	0.009	0.001	0.528	0.534	See	See
24	KNeighborsClassifier_brute_force	fit	100000	100000	2	0.005	0.001	0.294	0.0	1	100	0.009	0.001	0.612	0.616	See	See
27	KNeighborsClassifier_brute_force	fit	100000	100000	2	0.005	0.000	0.343	0.0	-1	100	0.009	0.001	0.496	0.497	See	See
30	KNeighborsClassifier_brute_force	fit	100000	100000	2	0.005	0.000	0.320	0.0	1	5	0.009	0.001	0.566	0.567	See	See
33	KNeighborsClassifier_brute_force	fit	100000	100000	2	0.005	0.000	0.337	0.0	1	1	0.009	0.001	0.521	0.523	See	See

	estimator	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_jobs	n_neighbors	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	KNeighborsClassifier_brute_force	predict	100000	1000	100	2.346	0.197	0.0	0.002	-1	1	0.471	0.006	4.980	4.980	See	See
2	KNeighborsClassifier_brute_force	predict	100000	1	100	0.028	0.004	0.0	0.028	-1	1	0.011	0.001	2.402	2.405	See	See
4	KNeighborsClassifier_brute_force	predict	100000	1000	100	3.136	0.101	0.0	0.003	-1	5	0.473	0.006	6.635	6.635	See	See
5	KNeighborsClassifier_brute_force	predict	100000	1	100	0.027	0.003	0.0	0.027	-1	5	0.012	0.001	2.311	2.316	See	See
7	KNeighborsClassifier_brute_force	predict	100000	1000	100	2.444	0.027	0.0	0.002	1	100	0.537	0.007	4.551	4.552	See	See
8	KNeighborsClassifier_brute_force	predict	100000	1	100	0.026	0.003	0.0	0.026	1	100	0.011	0.001	2.261	2.265	See	See
10	KNeighborsClassifier_brute_force	predict	100000	1000	100	3.139	0.063	0.0	0.003	-1	100	0.530	0.010	5.925	5.926	See	See
11	KNeighborsClassifier_brute_force	predict	100000	1	100	0.029	0.003	0.0	0.029	-1	100	0.012	0.001	2.403	2.411	See	See
13	KNeighborsClassifier_brute_force	predict	100000	1000	100	2.443	0.022	0.0	0.002	1	5	0.466	0.009	5.239	5.240	See	See
14	KNeighborsClassifier_brute_force	predict	100000	1	100	0.027	0.002	0.0	0.027	1	5	0.011	0.001	2.326	2.332	See	See
16	KNeighborsClassifier_brute_force	predict	100000	1000	100	1.622	0.011	0.0	0.002	1	1	0.471	0.013	3.443	3.445	See	See
17	KNeighborsClassifier_brute_force	predict	100000	1	100	0.024	0.001	0.0	0.024	1	1	0.012	0.001	2.098	2.102	See	See
19	KNeighborsClassifier_brute_force	predict	100000	1000	2	1.851	0.029	0.0	0.002	-1	1	0.105	0.008	17.626	17.671	See	See
20	KNeighborsClassifier_brute_force	predict	100000	1	2	0.006	0.002	0.0	0.006	-1	1	0.001	0.000	6.848	7.012	See	See
22	KNeighborsClassifier_brute_force	predict	100000	1000	2	2.809	0.070	0.0	0.003	-1	5	0.103	0.003	27.397	27.405	See	See
23	KNeighborsClassifier_brute_force	predict	100000	1	2	0.007	0.002	0.0	0.007	-1	5	0.001	0.000	10.120	10.229	See	See
25	KNeighborsClassifier_brute_force	predict	100000	1000	2	2.213	0.031	0.0	0.002	1	100	0.158	0.002	14.029	14.031	See	See
26	KNeighborsClassifier_brute_force	predict	100000	1	2	0.003	0.000	0.0	0.003	1	100	0.001	0.000	4.181	4.227	See	See
28	KNeighborsClassifier_brute_force	predict	100000	1000	2	2.779	0.060	0.0	0.003	-1	100	0.159	0.004	17.509	17.514	See	See
29	KNeighborsClassifier_brute_force	predict	100000	1	2	0.006	0.002	0.0	0.006	-1	100	0.001	0.000	8.151	8.185	See	See
31	KNeighborsClassifier_brute_force	predict	100000	1000	2	2.257	0.045	0.0	0.002	1	5	0.102	0.001	22.063	22.065	See	See
32	KNeighborsClassifier_brute_force	predict	100000	1	2	0.003	0.000	0.0	0.003	1	5	0.001	0.000	4.736	4.777	See	See
34	KNeighborsClassifier_brute_force	predict	100000	1000	2	1.317	0.014	0.0	0.001	1	1	0.101	0.002	13.039	13.042	See	See
35	KNeighborsClassifier_brute_force	predict	100000	1	2	0.002	0.000	0.0	0.002	1	1	0.001	0.000	3.311	3.340	See	See

KNeighborsClassifier_kd_tree

scikit-learn-intelex (2021.20210705.191215) vs. scikit-learn (1.0.dev0)

Speedup barplots

All estimators share the following parameters: algorithm=kd_tree.

WARNING! Mismatch between validation scores for 12 prediction (50.0%). The observed differences can be found in the diff_accuracy_scores column. The chosen difference threshold is 0.001 for accuracy_score. See details in the dataframe below.

	estimator	function	n_samples_train	n_samples	n_features	parameters_digest	dataset_digest	mean_duration_sklearn	std_duration_sklearn	n_iter	iteration_throughput	latency	algorithm	n_jobs	n_neighbors	accuracy_score_sklearn	mean_duration_sklearnex	std_duration_sklearnex	accuracy_score_sklearnex	speedup	std_speedup	diff_accuracy_scores
1	KNeighborsClassifier_kd_tree	predict	1000000	1000	10	fe8267e25dadb302ed498e50fabf7ef4	1eb6cf1a720a225efb91df0b529b0510	0.920315	1.186926	NaN	0.000087	0.000920	kd_tree	-1	1	0.929	0.128069	0.003834	0.910	7.186097	7.189316	0.019
4	KNeighborsClassifier_kd_tree	predict	1000000	1000	10	dc74b969bf622bc24ba3bc62c980983b	1eb6cf1a720a225efb91df0b529b0510	1.125627	0.559873	NaN	0.000071	0.001126	kd_tree	-1	5	0.946	0.231097	0.007563	0.941	4.870805	4.873413	0.005
7	KNeighborsClassifier_kd_tree	predict	1000000	1000	10	41accfcdcd5c50784bedf6164b63de99	1eb6cf1a720a225efb91df0b529b0510	6.058615	0.722357	NaN	0.000013	0.006059	kd_tree	1	100	0.951	0.694570	0.012779	0.940	8.722829	8.724305	0.011
10	KNeighborsClassifier_kd_tree	predict	1000000	1000	10	022f7445d43bb1dbc24dc3106c03cb93	1eb6cf1a720a225efb91df0b529b0510	3.511473	0.341730	NaN	0.000023	0.003511	kd_tree	-1	100	0.951	0.719420	0.009270	0.940	4.880975	4.881380	0.011
13	KNeighborsClassifier_kd_tree	predict	1000000	1000	10	84622ba45e941db642965553529e1941	1eb6cf1a720a225efb91df0b529b0510	1.879582	0.409067	NaN	0.000043	0.001880	kd_tree	1	5	0.946	0.244425	0.008042	0.941	7.689807	7.693969	0.005
16	KNeighborsClassifier_kd_tree	predict	1000000	1000	10	a9455565db1d8e052a783317c99744ff	1eb6cf1a720a225efb91df0b529b0510	1.018047	0.382193	NaN	0.000079	0.001018	kd_tree	1	1	0.929	0.130902	0.003550	0.910	7.777167	7.780026	0.019
19	KNeighborsClassifier_kd_tree	predict	1000	1000	2	fe8267e25dadb302ed498e50fabf7ef4	edf7cb014c2c0910e1c3aaaf8ae633f2	0.038381	0.016261	NaN	0.000417	0.000038	kd_tree	-1	1	0.891	0.000759	0.000260	0.879	50.537893	53.421117	0.012
22	KNeighborsClassifier_kd_tree	predict	1000	1000	2	dc74b969bf622bc24ba3bc62c980983b	edf7cb014c2c0910e1c3aaaf8ae633f2	0.034384	0.001957	NaN	0.000465	0.000034	kd_tree	-1	5	0.911	0.000931	0.000042	0.905	36.929226	36.966619	0.006
25	KNeighborsClassifier_kd_tree	predict	1000	1000	2	41accfcdcd5c50784bedf6164b63de99	edf7cb014c2c0910e1c3aaaf8ae633f2	0.050384	0.014551	NaN	0.000318	0.000050	kd_tree	1	100	0.894	0.005895	0.000193	0.917	8.547459	8.552046	0.023
28	KNeighborsClassifier_kd_tree	predict	1000	1000	2	022f7445d43bb1dbc24dc3106c03cb93	edf7cb014c2c0910e1c3aaaf8ae633f2	0.054541	0.011573	NaN	0.000293	0.000055	kd_tree	-1	100	0.894	0.007169	0.002378	0.917	7.607410	8.014863	0.023
31	KNeighborsClassifier_kd_tree	predict	1000	1000	2	84622ba45e941db642965553529e1941	edf7cb014c2c0910e1c3aaaf8ae633f2	0.032208	0.001287	NaN	0.000497	0.000032	kd_tree	1	5	0.911	0.001116	0.000486	0.905	28.854770	31.473653	0.006
34	KNeighborsClassifier_kd_tree	predict	1000	1000	2	a9455565db1d8e052a783317c99744ff	edf7cb014c2c0910e1c3aaaf8ae633f2	0.031884	0.003153	NaN	0.000502	0.000032	kd_tree	1	1	0.891	0.000621	0.000016	0.879	51.323294	51.340629	0.012

Raw results

	estimator	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_jobs	n_neighbors	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	KNeighborsClassifier_kd_tree	fit	1000000	1000000	10	2.844	0.034	0.028	0.0	-1	1	0.863	0.075	3.295	3.307	See	See
3	KNeighborsClassifier_kd_tree	fit	1000000	1000000	10	3.907	0.115	0.020	0.0	-1	5	0.833	0.022	4.691	4.692	See	See
6	KNeighborsClassifier_kd_tree	fit	1000000	1000000	10	3.972	0.119	0.020	0.0	1	100	0.791	0.016	5.020	5.021	See	See
9	KNeighborsClassifier_kd_tree	fit	1000000	1000000	10	3.920	0.089	0.020	0.0	-1	100	0.860	0.022	4.559	4.560	See	See
12	KNeighborsClassifier_kd_tree	fit	1000000	1000000	10	4.037	0.095	0.020	0.0	1	5	0.826	0.019	4.888	4.889	See	See
15	KNeighborsClassifier_kd_tree	fit	1000000	1000000	10	3.973	0.100	0.020	0.0	1	1	0.858	0.021	4.630	4.631	See	See
18	KNeighborsClassifier_kd_tree	fit	1000	1000	2	0.001	0.001	0.016	0.0	-1	1	0.005	0.004	0.209	0.270	See	See
21	KNeighborsClassifier_kd_tree	fit	1000	1000	2	0.001	0.000	0.021	0.0	-1	5	0.003	0.002	0.263	0.334	See	See
24	KNeighborsClassifier_kd_tree	fit	1000	1000	2	0.001	0.000	0.024	0.0	1	100	0.002	0.001	0.351	0.447	See	See
27	KNeighborsClassifier_kd_tree	fit	1000	1000	2	0.001	0.000	0.023	0.0	-1	100	0.001	0.000	0.615	0.622	See	See
30	KNeighborsClassifier_kd_tree	fit	1000	1000	2	0.001	0.000	0.021	0.0	1	5	0.001	0.000	0.665	0.671	See	See
33	KNeighborsClassifier_kd_tree	fit	1000	1000	2	0.001	0.000	0.021	0.0	1	1	0.001	0.000	0.682	0.685	See	See

	estimator	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_jobs	n_neighbors	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	KNeighborsClassifier_kd_tree	predict	1000000	1000	10	0.920	1.187	0.000	0.001	-1	1	0.128	0.004	7.186	7.189	See	See
2	KNeighborsClassifier_kd_tree	predict	1000000	1	10	0.003	0.001	0.000	0.003	-1	1	0.000	0.000	9.999	10.244	See	See
4	KNeighborsClassifier_kd_tree	predict	1000000	1000	10	1.126	0.560	0.000	0.001	-1	5	0.231	0.008	4.871	4.873	See	See
5	KNeighborsClassifier_kd_tree	predict	1000000	1	10	0.004	0.000	0.000	0.004	-1	5	0.000	0.000	8.379	8.609	See	See
7	KNeighborsClassifier_kd_tree	predict	1000000	1000	10	6.059	0.722	0.000	0.006	1	100	0.695	0.013	8.723	8.724	See	See
8	KNeighborsClassifier_kd_tree	predict	1000000	1	10	0.004	0.002	0.000	0.004	1	100	0.001	0.000	3.853	3.984	See	See
10	KNeighborsClassifier_kd_tree	predict	1000000	1000	10	3.511	0.342	0.000	0.004	-1	100	0.719	0.009	4.881	4.881	See	See
11	KNeighborsClassifier_kd_tree	predict	1000000	1	10	0.006	0.001	0.000	0.006	-1	100	0.001	0.000	6.081	6.218	See	See
13	KNeighborsClassifier_kd_tree	predict	1000000	1000	10	1.880	0.409	0.000	0.002	1	5	0.244	0.008	7.690	7.694	See	See
14	KNeighborsClassifier_kd_tree	predict	1000000	1	10	0.002	0.000	0.000	0.002	1	5	0.001	0.000	3.317	3.442	See	See
16	KNeighborsClassifier_kd_tree	predict	1000000	1000	10	1.018	0.382	0.000	0.001	1	1	0.131	0.004	7.777	7.780	See	See
17	KNeighborsClassifier_kd_tree	predict	1000000	1	10	0.001	0.000	0.000	0.001	1	1	0.000	0.000	3.263	3.709	See	See
19	KNeighborsClassifier_kd_tree	predict	1000	1000	2	0.038	0.016	0.000	0.000	-1	1	0.001	0.000	50.538	53.421	See	See
20	KNeighborsClassifier_kd_tree	predict	1000	1	2	0.004	0.002	0.000	0.004	-1	1	0.000	0.000	30.591	30.872	See	See
22	KNeighborsClassifier_kd_tree	predict	1000	1000	2	0.034	0.002	0.000	0.000	-1	5	0.001	0.000	36.929	36.967	See	See
23	KNeighborsClassifier_kd_tree	predict	1000	1	2	0.003	0.000	0.000	0.003	-1	5	0.000	0.000	16.705	17.134	See	See
25	KNeighborsClassifier_kd_tree	predict	1000	1000	2	0.050	0.015	0.000	0.000	1	100	0.006	0.000	8.547	8.552	See	See
26	KNeighborsClassifier_kd_tree	predict	1000	1	2	0.001	0.000	0.000	0.001	1	100	0.000	0.000	4.702	4.786	See	See
28	KNeighborsClassifier_kd_tree	predict	1000	1000	2	0.055	0.012	0.000	0.000	-1	100	0.007	0.002	7.607	8.015	See	See
29	KNeighborsClassifier_kd_tree	predict	1000	1	2	0.003	0.001	0.000	0.003	-1	100	0.000	0.000	14.842	15.994	See	See
31	KNeighborsClassifier_kd_tree	predict	1000	1000	2	0.032	0.001	0.000	0.000	1	5	0.001	0.000	28.855	31.474	See	See
32	KNeighborsClassifier_kd_tree	predict	1000	1	2	0.001	0.000	0.000	0.001	1	5	0.000	0.000	4.887	5.055	See	See
34	KNeighborsClassifier_kd_tree	predict	1000	1000	2	0.032	0.003	0.001	0.000	1	1	0.001	0.000	51.323	51.341	See	See
35	KNeighborsClassifier_kd_tree	predict	1000	1	2	0.001	0.000	0.000	0.001	1	1	0.000	0.000	5.482	5.664	See	See

KMeans_tall

scikit-learn-intelex (2021.20210705.191215) vs. scikit-learn (1.0.dev0)

Speedup barplots

All estimators share the following parameters: algorithm=full, n_clusters=3, max_iter=30, n_init=1, tol=1e-16.

Raw results

	estimator	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	n_iter	iteration_throughput	latency	init	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	KMeans_tall	fit	1000000	1000000	2	0.650	0.089	30	0.025	0.0	random	0.333	0.012	1.953	1.955	See	See
3	KMeans_tall	fit	1000000	1000000	2	0.713	0.024	30	0.022	0.0	k-means++	0.375	0.008	1.899	1.900	See	See
6	KMeans_tall	fit	1000000	1000000	100	8.114	0.229	30	0.099	0.0	random	4.441	0.139	1.827	1.828	See	See
9	KMeans_tall	fit	1000000	1000000	100	8.363	0.025	30	0.096	0.0	k-means++	4.615	0.054	1.812	1.812	See	See

	estimator	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	n_iter	iteration_throughput	latency	init	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	KMeans_tall	predict	1000000	1000	2	0.002	0.001	30	0.007	0.000	random	0.0	0.0	6.394	9.564	See	See
2	KMeans_tall	predict	1000000	1	2	0.002	0.000	30	0.000	0.002	random	0.0	0.0	11.848	11.931	See	See
4	KMeans_tall	predict	1000000	1000	2	0.002	0.001	30	0.007	0.000	k-means++	0.0	0.0	9.498	10.021	See	See
5	KMeans_tall	predict	1000000	1	2	0.002	0.000	30	0.000	0.002	k-means++	0.0	0.0	10.817	11.104	See	See
7	KMeans_tall	predict	1000000	1000	100	0.002	0.000	30	0.367	0.000	random	0.0	0.0	7.078	7.243	See	See
8	KMeans_tall	predict	1000000	1	100	0.002	0.000	30	0.000	0.002	random	0.0	0.0	9.616	9.716	See	See
10	KMeans_tall	predict	1000000	1000	100	0.002	0.001	30	0.332	0.000	k-means++	0.0	0.0	7.074	7.302	See	See
11	KMeans_tall	predict	1000000	1	100	0.002	0.000	30	0.000	0.002	k-means++	0.0	0.0	10.904	11.634	See	See

KMeans_short

scikit-learn-intelex (2021.20210705.191215) vs. scikit-learn (1.0.dev0)

Speedup barplots

All estimators share the following parameters: algorithm=full, n_clusters=300, max_iter=20, n_init=1, tol=1e-16.

WARNING! Mismatch between validation scores for 4 prediction (50.0%). The observed differences can be found in the diff_adjusted_rand_scores column. The chosen difference threshold is 0.001 for adjusted_rand_score. See details in the dataframe below.

	estimator	function	n_samples_train	n_samples	n_features	parameters_digest	dataset_digest	mean_duration_sklearn	std_duration_sklearn	n_iter	iteration_throughput	latency	algorithm	init	max_iter	n_clusters	n_init	tol	adjusted_rand_score_sklearn	mean_duration_sklearnex	std_duration_sklearnex	adjusted_rand_score_sklearnex	speedup	std_speedup	diff_adjusted_rand_scores
1	KMeans_short	predict	10000	1000	2	3db9c030f488d0e8ff350ae449da4627	058b7e3842b587a5c675518f0706f5ee	0.002383	0.000212	20	0.006714	0.000002	full	random	20	300	1	1.000000e-16	0.000126	0.000926	0.000754	-0.000965	2.572960	3.317346	0.001090
4	KMeans_short	predict	10000	1000	2	ac9b8cec4749455c0d1cd1a92c150716	058b7e3842b587a5c675518f0706f5ee	0.002230	0.000140	20	0.007174	0.000002	full	k-means++	20	300	1	1.000000e-16	0.001245	0.000786	0.000131	-0.000750	2.837247	2.876539	0.001995
7	KMeans_short	predict	10000	1000	100	3db9c030f488d0e8ff350ae449da4627	7f85b913f395ec54101a6738ea63a9a7	0.003614	0.000142	20	0.221346	0.000004	full	random	20	300	1	1.000000e-16	0.278733	0.001651	0.000094	0.293767	2.188862	2.192424	0.015034
10	KMeans_short	predict	10000	1000	100	ac9b8cec4749455c0d1cd1a92c150716	7f85b913f395ec54101a6738ea63a9a7	0.003929	0.000348	20	0.203638	0.000004	full	k-means++	20	300	1	1.000000e-16	0.317011	0.001654	0.000075	0.256968	2.374975	2.377420	0.060044

Raw results

	estimator	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	n_iter	iteration_throughput	latency	init	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	KMeans_short	fit	10000	10000	2	0.113	0.003	20	0.001	0.0	random	0.059	0.004	1.901	1.905	See	See
3	KMeans_short	fit	10000	10000	2	0.337	0.010	20	0.000	0.0	k-means++	0.154	0.010	2.187	2.191	See	See
6	KMeans_short	fit	10000	10000	100	0.372	0.005	20	0.022	0.0	random	0.294	0.004	1.264	1.264	See	See
9	KMeans_short	fit	10000	10000	100	1.245	0.021	20	0.006	0.0	k-means++	0.672	0.009	1.852	1.852	See	See

	estimator	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	n_iter	iteration_throughput	latency	init	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	KMeans_short	predict	10000	1000	2	0.002	0.000	20	0.007	0.000	random	0.001	0.001	2.573	3.317	See	See
2	KMeans_short	predict	10000	1	2	0.002	0.000	20	0.000	0.002	random	0.000	0.000	10.489	10.620	See	See
4	KMeans_short	predict	10000	1000	2	0.002	0.000	20	0.007	0.000	k-means++	0.001	0.000	2.837	2.877	See	See
5	KMeans_short	predict	10000	1	2	0.002	0.001	20	0.000	0.002	k-means++	0.000	0.000	11.001	11.929	See	See
7	KMeans_short	predict	10000	1000	100	0.004	0.000	20	0.221	0.000	random	0.002	0.000	2.189	2.192	See	See
8	KMeans_short	predict	10000	1	100	0.002	0.000	20	0.000	0.002	random	0.000	0.000	9.983	10.101	See	See
10	KMeans_short	predict	10000	1000	100	0.004	0.000	20	0.204	0.000	k-means++	0.002	0.000	2.375	2.377	See	See
11	KMeans_short	predict	10000	1	100	0.002	0.000	20	0.000	0.002	k-means++	0.000	0.000	9.805	9.991	See	See

LogisticRegression

scikit-learn-intelex (2021.20210705.191215) vs. scikit-learn (1.0.dev0)

Speedup barplots

All estimators share the following parameters: penalty=l2, dual=False, tol=0.0001, C=1.0, fit_intercept=True, intercept_scaling=1, class_weight=nan, random_state=nan, solver=lbfgs, max_iter=100, multi_class=auto, verbose=0, warm_start=False, n_jobs=nan, l1_ratio=nan.

WARNING! Mismatch between validation scores for 2 prediction (50.0%). The observed differences can be found in the diff_accuracy_scores column. The chosen difference threshold is 0.001 for accuracy_score. See details in the dataframe below.

	estimator	function	n_samples_train	n_samples	n_features	parameters_digest	dataset_digest	mean_duration_sklearn	std_duration_sklearn	n_iter	iteration_throughput	latency	C	class_weight	dual	fit_intercept	intercept_scaling	l1_ratio	max_iter	multi_class	n_jobs	penalty	random_state	solver	tol	verbose	warm_start	accuracy_score_sklearn	mean_duration_sklearnex	std_duration_sklearnex	accuracy_score_sklearnex	speedup	std_speedup	diff_accuracy_scores
1	LogisticRegression	predict	1000000	1000	100	f11be2529b0a77bc8fb5ee8de141e6b2	09c36ed6521e03974d0c134895f56c01	0.000578	0.000703	[20]	1.384545	5.778073e-07	1.0	NaN	False	True	1	NaN	100	auto	NaN	l2	NaN	lbfgs	0.0001	0	False	0.56	0.000938	0.001596	0.55	0.616274	1.216650	0.01
4	LogisticRegression	predict	1000	100	10000	f11be2529b0a77bc8fb5ee8de141e6b2	7daecaea01e5baa8c862f264e3c1c3b0	0.002624	0.000241	[26]	3.048718	2.624053e-05	1.0	NaN	False	True	1	NaN	100	auto	NaN	l2	NaN	lbfgs	0.0001	0	False	0.35	0.004787	0.001739	0.28	0.548167	0.583234	0.07

Raw results

	estimator	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	n_iter	iteration_throughput	latency	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	LogisticRegression	fit	1000000	1000000	100	18.399	0.242	[20]	0.043	0.000	3.282	0.035	5.607	5.607	See	See
3	LogisticRegression	fit	1000	1000	10000	1.701	0.843	[26]	0.047	0.002	1.383	0.028	1.230	1.231	See	See

	estimator	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	n_iter	iteration_throughput	latency	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	LogisticRegression	predict	1000000	1000	100	0.001	0.001	[20]	1.385	0.0	0.001	0.002	0.616	1.217	See	See
2	LogisticRegression	predict	1000000	1	100	0.000	0.000	[20]	0.010	0.0	0.000	0.000	0.282	0.292	See	See
4	LogisticRegression	predict	1000	100	10000	0.003	0.000	[26]	3.049	0.0	0.005	0.002	0.548	0.583	See	See
5	LogisticRegression	predict	1000	1	10000	0.000	0.000	[26]	0.606	0.0	0.001	0.000	0.145	0.145	See	See

Ridge

scikit-learn-intelex (2021.20210705.191215) vs. scikit-learn (1.0.dev0)

Speedup barplots

All estimators share the following parameters: alpha=1.0, fit_intercept=True, normalize=deprecated, copy_X=True, max_iter=nan, tol=0.001, solver=auto, random_state=nan.

WARNING! Mismatch between validation scores for 1 prediction (25.0%). The observed differences can be found in the diff_r2_scores column. The chosen difference threshold is 0.001 for r2_score. See details in the dataframe below.

	estimator	function	n_samples_train	n_samples	n_features	parameters_digest	dataset_digest	mean_duration_sklearn	std_duration_sklearn	n_iter	iteration_throughput	latency	alpha	copy_X	fit_intercept	max_iter	normalize	random_state	solver	tol	r2_score_sklearn	mean_duration_sklearnex	std_duration_sklearnex	r2_score_sklearnex	speedup	std_speedup	diff_r2_scores
1	Ridge	predict	1000	1000	10000	a70ae8dc5c059ec88cf27c61016aee2a	14fae294d530397144c65ba3209bf125	0.014073	0.000842	NaN	5.684483	0.000014	1.0	True	True	NaN	deprecated	NaN	auto	0.001	0.082567	0.022532	0.000934	0.122191	0.624594	0.62513	0.039624

Raw results

	estimator	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	Ridge	fit	1000	1000	10000	0.341	0.005	0.235	0.0	0.349	0.007	0.976	0.976	See	See
3	Ridge	fit	1000000	1000000	100	1.539	0.091	0.520	0.0	0.509	0.242	3.025	3.351	See	See

	estimator	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	Ridge	predict	1000	1000	10000	0.014	0.001	5.684	0.0	0.023	0.001	0.625	0.625	See	See
2	Ridge	predict	1000	1	10000	0.000	0.000	0.826	0.0	0.000	0.000	0.520	0.559	See	See
4	Ridge	predict	1000000	1000	100	0.000	0.000	4.419	0.0	0.000	0.000	0.482	0.674	See	See
5	Ridge	predict	1000000	1	100	0.000	0.000	0.009	0.0	0.000	0.000	0.629	0.663	See	See